{"id":21693521,"url":"https://github.com/kleinyuan/llama2-csv-webapp","last_synced_at":"2025-04-12T10:40:34.375Z","repository":{"id":217234103,"uuid":"743333769","full_name":"KleinYuan/llama2-csv-webapp","owner":"KleinYuan","description":"self host/local host llama2 based web app to chat with your csvs (multiple)","archived":false,"fork":false,"pushed_at":"2024-01-15T02:07:26.000Z","size":172,"stargazers_count":6,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-18T22:04:45.939Z","etag":null,"topics":["chatgpt","csv","datalake","large-language-models","llama2","llm","meta","openai","pandas","pandas-ai","pandasai","streamlit"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/KleinYuan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2024-01-15T02:00:24.000Z","updated_at":"2024-08-20T07:27:15.000Z","dependencies_parsed_at":"2024-01-15T06:45:04.177Z","dependency_job_id":"ad327313-db64-4304-812a-ebdd18857408","html_url":"https://github.com/KleinYuan/llama2-csv-webapp","commit_stats":null,"previous_names":["kleinyuan/llama2-csv-webapp"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KleinYuan%2Fllama2-csv-webapp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KleinYuan%2Fllama2-csv-webapp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KleinYuan%2Fllama2-csv-webapp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KleinYuan%2Fllama2-csv-webapp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KleinYuan","download_url":"https://codeload.github.com/KleinYuan/llama2-csv-webapp/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248556573,"owners_count":21124141,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["chatgpt","csv","datalake","large-language-models","llama2","llm","meta","openai","pandas","pandas-ai","pandasai","streamlit"],"created_at":"2024-11-25T18:20:39.163Z","updated_at":"2025-04-12T10:40:34.349Z","avatar_url":"https://github.com/KleinYuan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# llama2-csv-webapp\n\nShow case running a couple of lines of code to \n- launch a web app\n- with local hosted LLM, such as llama2, without exposing your data to external commercial products.\n- chat about csv\n\nI am trying to keep the code as simple / naive as possible to make it easy enough to read, instead of optimizing the robustness.\n\n## Machine Requirements\n\nThe \u003e= 24GB Memory GPUs (such as 3090ti, 4090, ...) is all you need. If your GPU memory is lower than that, just swap the local model with a smaller one.\n\nEverything below is tested on a Ubuntu 22.04 machine, in the native system with Anaconda.\n\n## Step by Step Guide\n\n### Install Python Dedpendencies\n\n`pip install -r requirements.txt`\n\n### Spin Up Local LLM Inference Server\n\nFollow [this](https://huggingface.co/docs/text-generation-inference/quicktour#quick-tour) or run the follows:\n\n```\nmodel=codellama/CodeLlama-7b-Instruct-hf\nvolume=$PWD/data\ndocker run --gpus all --shm-size 1g -p 8080:80 -v $volume:/data ghcr.io/huggingface/text-generation-inference:1.3 --model-id $model\n```\n\n(You can change `codellama/CodeLlama-7b-Instruct-hf` to smaller models if your GPU has low Memory)\n\n\n### Spin Up Streamlit Web App\n\n`streamlit run app.py`\n\nOpen `http://10.0.0.171:8501/` on your browser and you are all set!\n\n![demo](demo.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkleinyuan%2Fllama2-csv-webapp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkleinyuan%2Fllama2-csv-webapp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkleinyuan%2Fllama2-csv-webapp/lists"}